skills.rest
semaes111
semaes111COMMUNITY
Explore all skills by this author →
GitHub

persistent-memory-7layer

Orchestrate seven memory layers for AI agents across sessions.

Updated Apr 7, 2026
Search Tags:#redis#embeddings#supabase#memory#qdrant#consolidation#agent-memory
One-click install
npx skills add https://github.com/semaes111/PROYECTO-SKILLS --skill persistent-memory-7layer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: persistent-memory-7layer
Source: https://github.com/semaes111/PROYECTO-SKILLS/tree/main/05-SKILLS-DEVOPS-INFRA/memoria-persistente-7-capas
Command: npx skills add https://github.com/semaes111/PROYECTO-SKILLS --skill persistent-memory-7layer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Agents lose context between interactions and lack a structured, reliable way to store short-term working state, episodic conversation history, semantic embeddings, procedural SOPs, long-term facts, and calibration metrics; this Skill provides a unified 7-layer memory orchestration to preserve and surface relevant context across sessions.

Core Features & Use Cases

  • Seven distinct layers (L1–L7): working memory (Redis 1h), short-term (Redis 24h), episodic (Supabase), semantic (pgvector embeddings), procedural (protocols/SOPs), long-term facts (Supabase), and meta-memory for calibration and metrics.
  • Automated consolidation: nightly L2->L3->L6 consolidation, summarization of episodes into facts, and embedding of new facts into semantic memory for future retrieval.
  • Semantic search & tooling: cosine-similarity search over pgvector/Qdrant, HNSW indexing, health checks, watcher events, and protocol-driven task automation (n8n/webhooks).
  • Production-ready schema and migrations: SQL schema, triggers, row-level security policies, and seed protocols for briefing, meeting prep, consolidation, and critical alerts.
  • Use case: Run MEMU to keep conversational context and user preferences available to your assistant across days, enable meeting prep that aggregates related history, and automatically surface long-term facts during decision workflows.

Quick Start

Install and configure MEMU with Redis, Supabase (pgvector), and Qdrant, set environment variables for API keys, and start the TypeScript Express service to enable the 7-layer memory and nightly consolidation.

Frequently Asked Questions about persistent-memory-7layer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I maintain agent memory across sessions in production AI infrastructure?▼

You maintain agent memory across sessions by deploying a 7-layer memory orchestration system that stores working state, episodic history, semantic embeddings, and long-term facts, ensuring conversational context persists reliably across interactions.

What is the best way to structure short-term and long-term memory for conversational agents?▼

Structuring short-term and long-term memory for conversational agents requires distinct layers separating ephemeral Redis state, episodic Supabase history, pgvector semantic embeddings, procedural SOPs, and long-term facts for reliable context retrieval.

How does automated memory consolidation work for AI agents using Supabase and Redis?▼

Automated memory consolidation works by running nightly workflows that summarize episodic history into long-term facts, then embed those facts into semantic memory via pgvector to ensure relevant context surfaces during future retrieval.

Do I need Redis, Supabase, and Qdrant to enable persistent multi-layer agent memory?▼

You need Redis for ephemeral working and short-term layers, Supabase with pgvector for episodic and long-term fact storage, and Qdrant or a compatible vector store for semantic embedding initialization and cosine-similarity search.

Can I use pgvector embeddings for semantic search in an agent memory system?▼

Yes, you can use pgvector embeddings for semantic search in an agent memory system by indexing stored facts with HNSW and performing cosine-similarity retrieval to surface relevant conversational context during decision workflows.

When do I need multi-layer agent memory instead of simple session state?▼

You need multi-layer agent memory instead of simple session state when your application requires retaining user preferences, aggregating meeting prep history, and automatically surfacing procedural SOPs and long-term facts across multiple days.

Related Skills

Explore More Software Engineering Skills→
RaudbjornRaudbjorn
6

supabase

Guide Supabase backend development with edge functions, migrations, and RLS policies.

Community
Advanced
gonzalezpazmonicagonzalezpazmonica
47

semantic-memory

Search project memory using vector embeddings and cosine similarity.

Community
Intermediate
SoftSystemsStudioSoftSystemsStudio

n8n-workflow

Design, debug, and manage n8n automation workflows with MCP server integration.

Community
Advanced
myaiartist360-makermyaiartist360-maker

memory

Maintains structured fact files and chronological event logs for AI context retrieval via grep.

Community
Basic